MSc in CS (Moratuwa), Bsc Eng. (Hons) (Moratuwa)
Kushan Hewapathirana is an academic and professional with a primary focus on artificial intelligence, machine learning, and the broader field of data science. He is currently pursuing an MSc in Computer Science, specializing in Data Science, Engineering, and Analytics from the Department of Computer Science & Engineering at the University of Moratuwa. His MSc research is focused on the domain of Multi-document Summarization. He obtained his BSc Engineering (Hons) from the Department of Textile and Apparel Engineering, University of Moratuwa in 2021. Kushan is an Associate Member of the Institution of Engineers, Sri Lanka (IESL), and holds the position of Associate Engineer in the Engineering Council of Sri Lanka (ECSL). Since 2022, he has been working as a Machine Learning Engineer at ConscientAI, an AI technology company based in Sri Lanka.
Keywords: Natural Language Processing | Machine Learning / Deep Learning | Sinhala |
Theses: MSc Minor Component Research
Kushan Hewapathirana, "Towards Multi-document Summarisation in Low-resource Settings", University of Moratuwa, 2025
Conference Papers
Kushan Hewapathirana, Nisansa de Silva, and C D Athuraliya, "M2DS: Multilingual Dataset for Multi-document Summarisation", in International Conference on Computational Collective Intelligence, 2024, pp. 219--231. doi: 10.1007/978-3-031-70248-8_17
Kushan Hewapathirana, Nisansa de Silva, and C D Athuraliya, "Multi-Document Summarization: A Comparative Evaluation", in 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), 2023, pp. 19--24. doi: 10.1109/ICIIS58898.2023.10253581
Extended Abstracts
Kushan Hewapathirana, Nisansa de Silva, and C. D. Athuraliya, "Adapter-based Fine-tuning for PRIMERA", in 1st Applied Data Science \& Artificial Intelligence Symposium, April. 2025.
PI: Nisansa de Silva
We propose to advance natural language processing for low-resource settings by leveraging data augmentation, transfer learning, and model adaptation techniques to overcome the scarcity of annotated data and linguistic resources.
PI: Nisansa de Silva
We propose to build and analyze Sinhala language resources, datasets, and models to strengthen NLP research for this low-resource language, while connecting it to English and Tamil through bilingual lexicons, embeddings, and cross-lingual methods.
PI: Nisansa de Silva
We propose to advance automatic summarization and generation techniques, with a focus on aspect-aware methods that capture fine-grained information and sentiment within concise textual representations.